A Comparative Analysis of Neurosymbolic Methods for Link Prediction

Guillaume Delplanque, Luisa Werner, Nabil Layaïda, Pierre Geneves
Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, PMLR 284:674-696, 2025.

Abstract

Link prediction on knowledge graphs is relevant to various applications, such as recommendation systems, question answering, and entity search. This task has been approached from different perspectives: symbolic methods leverage rule-based reasoning but struggle with scalability and noise, while knowledge graph embeddings (KGE) represent entities and relations in a continuous space, enabling scalability but often neglecting logical constraints from ontologies. Recently, neurosymbolic approaches have emerged to bridge this gap by integrating embedding-based learning with symbolic reasoning. This paper provides a structured review of state-of-the-art neurosymbolic methods for link prediction. Beyond a qualitative analysis, a key contribution of this work is a comprehensive experimental benchmarking, where we systematically compare these methods on the same datasets using the same metrics. This unified experimental setup allows for a fair assessment of their strengths and limitations, bringing elements of answers to following key questions: How accurate are these methods? How scalable are they? How beneficial are they for different levels of provided knowledge and to which extent are they robust to incorrect knowledge?

Cite this Paper

BibTeX
@InProceedings{pmlr-v284-delplanque25a, title = {A Comparative Analysis of Neurosymbolic Methods for Link Prediction}, author = {Delplanque, Guillaume and Werner, Luisa and Laya\"{i}da, Nabil and Geneves, Pierre}, booktitle = {Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning}, pages = {674--696}, year = {2025}, editor = {H. Gilpin, Leilani and Giunchiglia, Eleonora and Hitzler, Pascal and van Krieken, Emile}, volume = {284}, series = {Proceedings of Machine Learning Research}, month = {08--10 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v284/main/assets/delplanque25a/delplanque25a.pdf}, url = {https://proceedings.mlr.press/v284/delplanque25a.html}, abstract = {Link prediction on knowledge graphs is relevant to various applications, such as recommendation systems, question answering, and entity search. This task has been approached from different perspectives: symbolic methods leverage rule-based reasoning but struggle with scalability and noise, while knowledge graph embeddings (KGE) represent entities and relations in a continuous space, enabling scalability but often neglecting logical constraints from ontologies. Recently, neurosymbolic approaches have emerged to bridge this gap by integrating embedding-based learning with symbolic reasoning. This paper provides a structured review of state-of-the-art neurosymbolic methods for link prediction. Beyond a qualitative analysis, a key contribution of this work is a comprehensive experimental benchmarking, where we systematically compare these methods on the same datasets using the same metrics. This unified experimental setup allows for a fair assessment of their strengths and limitations, bringing elements of answers to following key questions: How accurate are these methods? How scalable are they? How beneficial are they for different levels of provided knowledge and to which extent are they robust to incorrect knowledge?} }
Endnote
%0 Conference Paper %T A Comparative Analysis of Neurosymbolic Methods for Link Prediction %A Guillaume Delplanque %A Luisa Werner %A Nabil Layaïda %A Pierre Geneves %B Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning %C Proceedings of Machine Learning Research %D 2025 %E Leilani H. Gilpin %E Eleonora Giunchiglia %E Pascal Hitzler %E Emile van Krieken %F pmlr-v284-delplanque25a %I PMLR %P 674--696 %U https://proceedings.mlr.press/v284/delplanque25a.html %V 284 %X Link prediction on knowledge graphs is relevant to various applications, such as recommendation systems, question answering, and entity search. This task has been approached from different perspectives: symbolic methods leverage rule-based reasoning but struggle with scalability and noise, while knowledge graph embeddings (KGE) represent entities and relations in a continuous space, enabling scalability but often neglecting logical constraints from ontologies. Recently, neurosymbolic approaches have emerged to bridge this gap by integrating embedding-based learning with symbolic reasoning. This paper provides a structured review of state-of-the-art neurosymbolic methods for link prediction. Beyond a qualitative analysis, a key contribution of this work is a comprehensive experimental benchmarking, where we systematically compare these methods on the same datasets using the same metrics. This unified experimental setup allows for a fair assessment of their strengths and limitations, bringing elements of answers to following key questions: How accurate are these methods? How scalable are they? How beneficial are they for different levels of provided knowledge and to which extent are they robust to incorrect knowledge?
APA
Delplanque, G., Werner, L., Layaïda, N. & Geneves, P.. (2025). A Comparative Analysis of Neurosymbolic Methods for Link Prediction. Proceedings of The 19th International Conference on Neurosymbolic Learning and Reasoning, in Proceedings of Machine Learning Research 284:674-696 Available from https://proceedings.mlr.press/v284/delplanque25a.html.

Related Material